检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Xiao, Li Zhu, Cheng Liu, Junjun Luo, Chunlong Liu, Peifang Zhao, Yi Key Laboratory of Intelligent Information Processing Advanced Computer Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China Tianjin Medical University Cancer Institute Hospital

Deep learning object detection algorithm has been widely used in medical image analysis. Currently all the object detection tasks are based on the data annotated with object classes and their bounding boxes. On the other hand, medical images such as mammography usually contain normal regions or objects that are similar to the lesion region, and may be misclassified in the testing stage if they are not taken care of. In this paper, we address such problem by introducing a novel top likelihood loss together with a new sampling procedure to select and train the suspected target regions, as well as proposing a similarity loss to further identify suspected targets from targets. Mean average precision (mAP) according to the predicted targets and specificity, sensitivity, accuracy, AUC values according to classification of patients are adopted for performance comparisons. We firstly test our proposed method on a private dense mammogram dataset. Results show that our proposed method greatly reduce the false positive rate and the specificity is increased by 0.25 on detecting mass type cancer. It is worth mention that dense breast typically has a higher risk for developing breast cancers and also are harder for cancer detection in diagnosis, and our method outperforms a reported result from performance of radiologists. Our method is also validated on the public Digital Database for Screening Mammography (DDSM) dataset, brings significant improvement on mass type cancer detection and outperforms the most state-of-the-art work. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

ASPCNet: A Deep Adaptive Spatial Pattern Capsule Network for Hyperspectral Image Classification

arXiv

引用

arXiv 2021年

作者： Wang, Jinping Tan, Xiaojun Lai, Jianhuang Li, Jun Xiang, Canqun School of Intelligent Systems Engineering Sun Yat-sen University Guangzhou510006 China Key Laboratory of Machine Intelligence and Advanced Computing School of Computer Science and Engineering Sun Yatsen University Ministry of Education Guangzhou510006 China Zhuhai519082 China College of Electronics and Information Engineering Shenzhen University Shenzhen518060 China

Previous studies have shown the great potential of capsule networks for the spatial contextual feature extraction from hyperspectral images (HSIs). However, the sampling locations of the convolutional kernels of capsules are fixed and cannot be adaptively changed according to the inconsistent semantic information of HSIs. Based on this observation, this paper proposes an adaptive spatial pattern capsule network (ASPCNet) architecture by developing an adaptive spatial pattern (ASP) unit, that can rotate the sampling location of convolutional kernels on the basis of an enlarged receptive field. Note that this unit can learn more discriminative representations of HSIs with fewer parameters. Specifically, two cascaded ASP-based convolution operations (ASPConvs) are applied to input images to learn relatively high-level semantic features, transmitting hierarchical structures among capsules more accurately than the use of the most fundamental features. Furthermore, the semantic features are fed into ASP-based conv-capsule operations (ASPCaps) to explore the shapes of objects among the capsules in an adaptive manner, further exploring the potential of capsule networks. Finally, the class labels of image patches centered on test samples can be determined according to the fully connected capsule layer. Experiments on three public datasets demonstrate that ASPCNet can yield competitive performance with higher accuracies than state-of-the-art methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Dimensional Optimization of a 3-DOF Translational PKM Considering Transmission Properties

引用

International Journal of Automation and computing 2019年第6期16卷 748-760页

作者： Song Lu Yang-Min Li Bing-Xiao Ding Department of Electromechanical Engineering University of MacaoTaipaMacao 853China Department of Industrial and Systems Engineering The Hong Kong Polytechnic UniversityKowloonHong Kong 852China Tianjin Key Laboratory of the Design and Intelligent Control of the Advanced Mechatronical System Tianjin University of TechnologyTianjin 300384China

Multi-objective dimensional optimization of parallel kinematic manipulators(PKMs) remains a challenging and worthwhile research endeavor. This paper presents a straightforward and systematic methodology for implementing the structure optimization analysis of a 3-prismatic-universal-universal(PUU) PKM when simultaneously considering motion transmission, velocity transmission and acceleration transmission. Firstly, inspired by a planar four-bar linkage mechanism, the motion transmission index of the spatial parallel manipulator is based on transmission angle which is defined as the pressure angle amongst limbs. Then, the velocity transmission index and acceleration transmission index are derived through the corresponding kinematics model. The multi-objective dimensional optimization under specific constraints is carried out by the improved non-dominated sorting genetic algorithm(NSGA Ⅱ), resulting in a set of Pareto optimal solutions. The final chosen solution shows that the manipulator with the optimized structure parameters can provide excellent motion, velocity and acceleration transmission properties.

关键词： Multi-objective optimization parallel kinematic manipulator transmission property non-dominated sorting genetic algorithm(NSGA Ⅱ)

来源：评论

学校读者我要写书评

暂无评论

Detection of Deepfake videos using long distance attention

arXiv

引用

arXiv 2021年

作者： Lu, Wei Liu, Lingyi Luo, Junwei Zhao, Xianfeng Zhou, Yicong Huang, Jiwu School of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100195 China School of Cyber Security University of Chinese Academy of Sciences Beijing100195 China Department of Computer and Information Science University of Macau 999078 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China

With the rapid progress of deepfake techniques in recent years, facial video forgery can generate highly deceptive video contents and bring severe security threats. And detection of such forgery videos is much more urgent and challenging. Most existing detection methods treat the problem as a vanilla binary classification problem. In this paper, the problem is treated as a special fine-grained classification problem since the differences between fake and real faces are very subtle. It is observed that most existing face forgery methods left some common artifacts in the spatial domain and time domain, including generative defects in the spatial domain and inter-frame inconsistencies in the time domain. And a spatial-temporal model is proposed which has two components for capturing spatial and temporal forgery traces in global perspective respectively. The two components are designed using a novel long distance attention mechanism. The one component of the spatial domain is used to capture artifacts in a single frame, and the other component of the time domain is used to capture artifacts in consecutive frames. They generate attention maps in the form of patches. The attention method has a broader vision which contributes to better assembling global information and extracting local statistic information. Finally, the attention maps are used to guide the network to focus on pivotal parts of the face, just like other fine-grained classification methods. The experimental results on different public datasets demonstrate that the proposed method achieves the state-of-the-art performance, and the proposed long distance attention method can effectively capture pivotal parts for face forgery. Copyright © 2021, The Authors. All rights reserved.

关键词： Time domain analysis

来源：评论

学校读者我要写书评

暂无评论

NURBS Interpolator With Pre-compensation Based on Discrete Inverse Transfer Function for CNC High-precision Machining

Research Square

引用

Research Square 2021年

作者： Wang, Taiyong Cao, Libo Zhang, Yongbin Dong, Jingchuan Jia, Songhui Tian, Chong Liu, Qingjian Renai College Tianjin University Tianjin301636 China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China School of Mechanical Engineering Tianjin University No.135 YaGuan Road Jinnan District Tianjin300354 China

In the field of CNC machining, high-speed and high-precision machining has been regarded as the key research by many scholars. In conventional methods, high-speed machining and high-precision machining are contradictory. It is inevitable to reduce the feedrate to improve the processing accuracy. In the paper, a pre-compensation based on discrete inverse transfer function (PDIT) theory is proposed. PDIT is able to improve machining accuracy by reducing contour errors without decreasing feedrate. The proposed PDIT theory is divided into three parts, NURBS interpolator, feedrate scheduling, and interpolator with pre-compensation. The NURBS interpolator has greatly advantage to interpolate the parameter curve directly. Therefore, the paper adopts the NURBS interpolator to accomplish interpolation. In the feedrate scheduling, S-type flexible acceleration and deceleration are used for path planning, and the maximum starting feedrate is obtained with the feedrate constraint. In the interpolator with pre-compensation, the NURBS interpolator is pre-compensated by PDIT. For inputs, the response of transfer function reach steady-state response with a little time. Before reaching steady-state response, the unsteady response exists in the transfer function. The unsteady response usually sustains tens of interpolation periods and must be lead contour error in machining. Hence, the PDIT theory is employed to compensate the contour error causing by the unsteady response of transfer function to NURBS interpolator. The drive system is a transfer function, so the unsteady response of drive system cause machining errors before reaching the steady-state response. In the paper, the NURBS interpolator is pre-compensated by PDIT theory before the drive system to reduce contour errors and improve machining accuracy. Finally, the performance of the proposed PDIT is evaluated by simulation experiments. The experimental results illustrate that PDIT theory obviously improve the machining accura

关键词： Transfer functions

来源：评论

学校读者我要写书评

暂无评论

Non-reciprocity of energy transfer derived from cubic stiffness-induced nonlinear phenomena

引用

Results in Physics 2025年 73卷

作者： Kong, Na Sun, Min Chen, Jianen Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin 300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin 300384 China School of Science Tianjin Chengjian University Tianjin 300384 China

Introducing purely nonlinear elastic elements can induce rich dynamic behaviors, such as bifurcations, jumps and isolated resonance curves, to linear systems. Therefore, these elements are suitable for constructing strong non-reciprocity of vibration energy transfer. First, the energy transfer along reciprocal directions in a three-degree-of-freedom system is investigated, where three oscillators are connected by cubic springs. The semi-analytical solutions of the system are obtained using the complexification-averaging method and the least squares method. The results are compared against numerical solutions obtained by the Runge-Kutta method. The excitation amplitude range that produces strong non-reciprocity of vibration energy is analyzed. The jump phenomenon under combined excitation is investigated, and a trigger method for constructing non-reciprocity using an impulse is proposed. Then, an oscillator chain with cubic stiffness and scaling parameters is embedded into a multi-degree-of-freedom linear oscillator system to further explore the effect of cubic stiffness. Energy transfer along two directions is compared by exciting the leftmost oscillator and the rightmost oscillator. Moreover, the trigger effect of the impulse on non-reciprocity is demonstrated. The results show significant differences in vibration energy transfer within three distinct frequency bands. The critical points between reciprocal and non-reciprocal states are obtained, and the three stages of reciprocity related to excitation amplitude are analyzed. Lastly, the modulation effect of the cubic stiffness on non-reciprocity is conducted by comparing the energy of the output oscillator. © 2025 The Authors

关键词： Cubic stiffness Energy transfer Jump phenomenon Non-reciprocity

来源：评论

学校读者我要写书评

暂无评论

Fractional Modeling and Dynamic Analysis of Two Kinds of Viscoelastic Thin Plates with Gaussian White Noise

SSRN

引用

SSRN 2023年

作者： Deng, Jinna Liu, Qiumei Yang, Aimin Chen, Yiming College of Science North China University of Science and Technology Tangshan063210 China Hebei Key Laboratory of Data Science and Application North China University of Science and Technology Tangshan063210 China The Key Laboratory of Engineering Computing in Tangshan City North China University of Science and Technology Tangshan063210 China Tangshan Intelligent Industry and Image Processing Technology Innovation Center North China University of Science and Technology Tangshan063210 China Hebei Engineering Research Center for the Intelligentization of Iron Ore Optimization and Ironmaking Raw Materials Preparation Processes North China University of Science and Technology Tangshan063210 China School of Science Yanshan University Qinhuangdao066004 China LE STUDIUM Loire Valley Institute for Advanced Studies Orléans & Tours Orléans45000 France

According to fractional order model, the governing equation of viscoelastic plate is established. Using the properties of the shifted Bernstein polynomials, the fractional order equation of viscoelastic plate is resolved, the conversion of fractional differential equations to algebraic equations, and operator matrices represented by Kronecker products are solved in the domain. The convergence study validates the algorithm's efficacy and precision in solving differential equations. The displacement of viscoelastic metal thin plate under different external loads (uniform distribution and linear distribution), the effect of white Gaussian noise on the thin metal plate displacement, the effect of different boundary conditions on thin metal plate displacement under harmonic load are studied, the displacements of metal and polymer plates under different loads are contrasted and stress and strain relationship of two kinds of plates are discussed. Based on the outcomes, it can be concluded that the shift Bernstein polynomial approach is useful for numerically simulating viscoelastic plates. © 2023, The Authors. All rights reserved.

关键词： Gaussian noise (electronic)

来源：评论

学校读者我要写书评

暂无评论

Palmprint recognition with deep convolutional features 12th

Palmprint recognition with deep convolutional features

引用

12th Chinese conference on Advances in Image and Graphics Technologies, IGTA 2017

作者： Sun, Qiule Zhang, Jianxin Yang, Aoqi Zhang, Qiang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian Dalian China

ISBN: (纸本)9789811073885

Palmprint recognition has become popular and significant in many fields because of its high efficiency and accuracy in personal identification. In this paper, we present a scheme for palmprint features extraction based on deep convolutional neural network (CNN). The CNN, which naturally integrates low/mid/high-level feature, performs excellently in processing images, video and speech. We extract the palmprint features using the CNN-F architecture, and exactly evaluate the convolutional features from different layers in the network for both identification and verification tasks. The experimental results on public PolyU palmprint database illuminate that palmprint features from the CNN-F respectively achieve the optimal identification rate of 100% and verification accuracy of EER= 0.25%, which demonstrate the effectiveness and reliability of the proposed palmprint CNN features. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

Global Dynamics and Optimal design of a New Highly Efficient Nonlinear Energy Sink Based on Magnetic-Elastic Impacts with Negative Stiffness

Research Square

引用

Research Square 2021年

作者： Li, Shuangbao Wang, Tingting Chen, Jianen Research Institute of Science and Technology Innovation Civil Aviation University of China Tianjin300300 China College of Science Civil Aviation University of China Tianjin300300 China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China

A new highly efficient elastic-impact bistable nonlinear energy sink (EI-BNES) based on magnetic-elastic impacts with negative stiffness and bistability is proposed and optimized through global dynamical analysis. The EI-BNES has better robustness and higher energy dissipation rates with nearly more than 96.5% for broadband impulsive excitations than the traditional cubic NESs and single bistable NESs. The structure of negative stiffness impacts is realized by reasonable layout of permanent ring magnets and springs. A two-degree-of-freedom (two-DOF) elastic-impact system is established to describe the coupled nonlinear interaction between the main structure and the attached EI-BNES. A global Melnikov reduction analysis (GMRA) is proposed to study global dynamics and homoclinic bifurcations of the reduced two-dimensional subsystem, which is used to explain the mechanism of nonlinear targeted energy transfer (TET) and detect the threshold of impulsive amplitudes of EI-BNES for in-well and compound motions between in-well and cross-well resonance responses. A special type of saddle-center equilibrium points is also found in the non-smooth system of the EI-BNES and can be used to effectively increase the energy dissipation rates. The optimal design criterion of the tuned EI-BNES for better dissipation performance is also first discussed based on the GMRA and numerical techniques for calculating the Melnikov function of the non-smooth systems. The effectiveness of the analytical GMRA is also verified by numerical simulations. © 2021, CC BY.

关键词： Stiffness

来源：评论

学校读者我要写书评

暂无评论

Term translation extraction from historical classics using modern Chinese explanation 17th

Term translation extraction from historical classics using m...

引用

17th China National Conference on Computational Linguistics, CCL 2018 and 6th International Symposium on Natural Language Processing Based on Naturally Annotated Big Data, NLP-NABD 2018

作者： Wu, Xiaoting Zhao, Hanyu Che, Chao Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian116622 China

ISBN: (纸本)9783030017156

Extracting term translation pairs is of great help for Chinese historical classics translation since term translation is the most time-consuming and challenging part in the translation of historical classics. However, it is tough to recognize the terms directly from ancient Chinese due to the flexible syntactic of ancient Chinese and the word segmentation errors of ancient Chinese will lead to more errors in term translation extraction. Considering most of the terms in ancient Chinese are still reserved in modern Chinese and the terms in modern Chinese are more easily to be identified, we propose a term translation extracting method using multi-features based on character-based model to extract historical term translation pairs from modern Chinese-English corpora instead of ancient Chinese-English corpora. Specifically, we first employ character-based BiLSTM-CRF model to identify historical terms in modern Chinese without word segmentation, which avoids word segmentation error spreading to the term alignment. Then we extract English terms according to initial capitalization rules. At last, we align the English and Chinese terms based on co-occurrence frequency and transliteration feature. The experiment on Shiji demonstrates that the performance of the proposed method is far superior to the traditional method, which confirms the effectiveness of using modern Chinese as a substitute. © Springer Nature Switzerland AG 2018.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：